Histopathological Image Segmentation Based on Probabilistic Graphical Model
-
摘要: 该文目的在于设计一种病理图像分割的方法,解决病理图像中复杂纹理背景上的粘连与部分重叠目标的识别与分 割的问题。通过构造适合于病理图像分割的混合概率图模型,分别利用无向图与有向图,对细胞核位置、轮廓对于区域及边 缘信息的概率依赖关系进行统计建模,研究上述构造的图模型中的参数估计方法,设计与实现基于上述构造的概率图模型的 病理图像分割算法,实验表明该方法提高了病理图像中细胞核的识别与轮廓勾勒的准确性。Abstract: The purpose of this paper is to design a method of pathological image segmentation, which can solve the problem of recognition and segmentation of conglutinated and partially overlapped objects on the background of complex texture in pathological image.In this paper a mixed probabilistic graphical model was constructed which is suitable for pathological image segmentation. By using undirected graph and directed graph, this paper built statistical models of the probability dependence of nuclear position, contour on region and edge information, and also researched the parameter estimation method in the graphical model, designed and implemented the pathological image segmentation algorithm based on the probabilistic graphical model. The experiment shows this method improves the accuracy of recognition of nuclei in pathological images.
-
[1] 李迎春.数据挖掘中决策树分类算法的研究[D].长沙:湖南师范大学,2015. [2] 林益峰.决策树算法在学生成绩预测中的应用[D].宁波:宁波大学,2019. [3] 董立岩,隋鹏,孙鹏,等.基于半监督学习的朴素贝叶斯分类新算法[J].吉林大学学报(工学版),2016,46(3):884-889. [4] 杨帆,何正伟,何帆.基于深度网络和船舶交通流的航道水深预测方法研究[J].武汉理工大学学报(交通科学与工程版),2019,43(1):130-135. [5] 高艳山.基于支持向量机的分类算法研究[D].青岛:山东科技大学,2012. -
点击查看大图
计量
- 文章访问数: 148
- HTML全文浏览量: 10
- PDF下载量: 19
- 被引次数: 0
下载: